On-line Estimators for Ad-hoc Task Execution : Learning Types and Parameters of Teammates for Effective Teamwork JAAMAS Track

do Carmo Alves, Matheus Ap and Yourdshahi, Elnaz Shafipour and Varma, Amokh and Marcolino, Leandro Soriano and Ueyama, Jó and Angelov, Plamen (2023) On-line Estimators for Ad-hoc Task Execution : Learning Types and Parameters of Teammates for Effective Teamwork JAAMAS Track. In: Proceedings of AAMAS-2023 :. Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, 2023-M . ACM, GBR, pp. 140-142. ISBN 9781450394321

Text (alves2023oeate_jaamas_track) - Accepted Version
Download (0B)

Text (alves2023oeate_jaamas_track) - Accepted Version
Download (0B)

Text (alves2023oeate_jaamas_track) - Accepted Version
Download (0B)

Text (alves2023oeate_jaamas_track) - Accepted Version
Download (0B)

Text (alves2023oeate_jaamas_track) - Accepted Version
Download (0B)

Text (alves2023oeate_jaamas_track) - Accepted Version
Download (0B)

Text (alves2023oeate_jaamas_track) - Accepted Version
Download (0B)

Text (alves2023oeate_jaamas_track) - Accepted Version
Download (0B)

Text (alves2023oeate_jaamas_track)
alves2023oeate_jaamas_track.pdf - Accepted Version
Download (941kB)

Abstract

In this paper, we present On-line Estimators for Ad-hoc Task Execution (OEATE), a novel algorithm for teammates' type and parameter estimation in decentralised task execution. We show theoretically that our algorithm can converge to perfect estimations, under some assumptions, as the number of tasks increases. Empirically, we show better performance against our baselines while estimating type and parameters in several different settings. This is an extended abstract of our JAAMAS paper available online [9].